import pandas as pd
import plotly.express as px

from plotly.offline import init_notebook_mode
init_notebook_mode()

# Read the CSV file with proper parameters
df = pd.read_csv('../data/capture_fisheries.csv', skiprows=4)  # Skip the header rows
df = df.dropna(how='all')  # Drop empty rows

# Melt the DataFrame to transform years into rows
years = [str(year) for year in range(1960, 2025)]
df_melted = df.melt(
    id_vars=["Country Name", "Country Code", "Indicator Name", "Indicator Code"],
    value_vars=years,
    var_name="Year",
    value_name="Capture Production (metric tons)"
)

# Convert to numeric and clean data
df_melted['Year'] = pd.to_numeric(df_melted['Year'])
df_melted['Capture Production (metric tons)'] = pd.to_numeric(
    df_melted['Capture Production (metric tons)'], errors='coerce'
)
df_melted = df_melted.dropna(subset=['Capture Production (metric tons)'])

# Calculate world totals by year
world_totals = df_melted.groupby('Year')['Capture Production (metric tons)'].sum().reset_index()

# Create the visualization
fig = px.line(
    world_totals,
    x='Year',
    y='Capture Production (metric tons)',
    title='World Total Capture Fisheries Production (1960-2024)',
    labels={'Capture Production (metric tons)': 'Total Capture (metric tons)'},
    markers=True
)

# Customize the layout
fig.update_layout(
    xaxis_title='Year',
    yaxis_title='Total Capture Production (metric tons)',
    hovermode='x unified',
    showlegend=False,
    template='plotly_white'
)

fig.update_traces(
    hovertemplate='<b>Year:</b> %{x}<br><b>Total Capture:</b> %{y:,} metric tons'
)

fig.show()